© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117177
    Prev
    Next
    INDEX
    Explanations

    concepts related to emotional honesty in performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    'gc
    -0.07
    ied
    -0.06
    esa
    -0.06
    se
    -0.06
    us
    -0.06
    eing
    -0.06
    usi
    -0.06
    626
    -0.06
    ja
    -0.05
    ãģ¨ãģĵãĤį
    -0.05
    POSITIVE LOGITS
    omanip
    0.07
    adel
    0.07
    adolu
    0.07
    rawer
    0.07
     Dup
    0.06
    essen
    0.06
    ạ
    0.06
    Uvs
    0.06
     McGu
    0.06
    asaki
    0.06
    Activations Density 0.493%

    No Known Activations